Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3012 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9261. Min Range: -1.9261

Max Act: 1.9261. Min Act: -0.0000

Data Index: 740696 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 1.9261. Min Range: -1.9261

Max Act: 1.8112. Min Act: -0.0000

Data Index: 344639 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 1.9261. Min Range: -1.9261

Max Act: 1.6305. Min Act: -0.0000

Data Index: 384494 (C4 (Web Text))

Max Activating Token Index: 903

Text #3

Max Range: 1.9261. Min Range: -1.9261

Max Act: 1.5924. Min Act: -0.0000

Data Index: 1082896 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 1.9261. Min Range: -1.9261

Max Act: 1.4828. Min Act: -0.0000

Data Index: 1015073 (C4 (Web Text))

Max Activating Token Index: 441

Text #5

Max Range: 1.9261. Min Range: -1.9261

Max Act: 1.4685. Min Act: -0.0000

Data Index: 994481 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 1.9261. Min Range: -1.9261

Max Act: 1.4424. Min Act: -0.0000

Data Index: 868719 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 1.9261. Min Range: -1.9261

Max Act: 1.5853. Min Act: -0.0000

Data Index: 285708 (C4 (Web Text))

Max Activating Token Index: 583

Text #8

Max Range: 1.9261. Min Range: -1.9261

Max Act: 1.4824. Min Act: -0.0000

Data Index: 536791 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 1.9261. Min Range: -1.9261

Max Act: 1.4230. Min Act: -0.0000

Data Index: 611014 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 1.9261. Min Range: -1.9261

Max Act: 1.3708. Min Act: -0.0000

Data Index: 960658 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 1.9261. Min Range: -1.9261

Max Act: 1.3542. Min Act: -0.0000

Data Index: 404129 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 1.9261. Min Range: -1.9261

Max Act: 1.3536. Min Act: -0.0000

Data Index: 74982 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 1.9261. Min Range: -1.9261

Max Act: 1.4069. Min Act: -0.0000

Data Index: 902910 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 1.9261. Min Range: -1.9261

Max Act: 1.4272. Min Act: -0.0000

Data Index: 900158 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 1.9261. Min Range: -1.9261

Max Act: 1.2699. Min Act: -0.0000

Data Index: 945762 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 1.9261. Min Range: -1.9261

Max Act: 1.3545. Min Act: -0.0000

Data Index: 252779 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 1.9261. Min Range: -1.9261

Max Act: 1.2993. Min Act: -0.0000

Data Index: 160052 (C4 (Web Text))

Max Activating Token Index: 545

Text #18

Max Range: 1.9261. Min Range: -1.9261

Max Act: 1.3331. Min Act: -0.0000

Data Index: 868570 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 1.9261. Min Range: -1.9261

Max Act: 1.2941. Min Act: -0.0000

Data Index: 162047 (C4 (Web Text))

Max Activating Token Index: 286